[Bugfix] Make compressed-tensors MoEs respect ignored layers (#28878)

Signed-off-by: HDCharles <charlesdavidhernandez@gmail.com>

.buildkite/test-pipeline.yaml

@@ -632,6 +632,7 @@ steps:
   # we can only upgrade after this is resolved
   # TODO(jerryzh168): resolve the above comment
   - uv pip install --system torchao==0.13.0 --index-url https://download.pytorch.org/whl/cu129
+  - uv pip install --system conch-triton-kernels
   - VLLM_TEST_FORCE_LOAD_FORMAT=auto pytest -v -s quantization/ --ignore quantization/test_blackwell_moe.py
 
 - label: LM Eval Small Models # 53min